ngxson/llama.cpp

Pull Requests Commits

server: clean up using_chatml variable

ngxson committed 1 year ago

Verified 1a274064

server: validate "--chat-template" argument

ngxson committed 1 year ago

ebe30795

server: format_llama2: remove BOS

ngxson committed 1 year ago

7efef47d

server: rename template mistral to llama2

ngxson committed 1 year ago

269437e4

server: fix typo

ngxson committed 1 year ago

27976c31

server: add mistral chat template

ngxson committed 1 year ago

2ebedda3

llama : do not print "offloading layers" message in CPU-only builds (#5416)

slaren committed 1 year ago

Verified 41f308f5

Fix f16_sycl cpy call from Arc (#5411)

abhilash1910 committed 1 year ago

Verified 6e99f2a0

llava : add missing .py, and fix paths in README.md (#5414)

danbev committed 1 year ago

Verified ff4ff05c

fix trailing whitespace (#5407)

JohannesGaessler committed 1 year ago

Verified b7b74cef

llama : fix MiniCPM (#5392)

runfuture committed 1 year ago

Verified 4aa43fab

llava: fix typo/formatting in README.md (#5405)

danbev committed 1 year ago

Verified a6e514a8

sampling: fix top_k <= 0 (#5388)

JohannesGaessler committed 1 year ago

Verified 26d4efd1

tests : .gitignore obj files

ggerganov committed 1 year ago

Verified 8504d2d0

CMAKE_OSX_ARCHITECTURES for MacOS cross compilation (#5393)

Xarbirus committed 1 year ago

Verified c4fbb671

fix typo in readme (#5399)

ebeyabraham committed 1 year ago

Verified 8c933b70

Add Ava in the list of llama.cpp UIs (#4362)

cztomsik committed 1 year ago

Verified b906596b

CUDA: fixed mmvq kernel for bs 2,3,4 and -sm row (#5386)

JohannesGaessler committed 1 year ago

Verified aa7ab99b

[SYCL] update install make by w64devkit (#5297)

NeoZhangJianyu committed 1 year ago

Verified 10afa6f1

llava-cli : always tokenize special tokens (#5382)

jxy committed 1 year ago

Verified 0ef46da6

Basic Vulkan Multi-GPU implementation (#5321)

0cc4m committed 1 year ago

Verified ee1628bd

readme : modernize (#5379)

netrunnereve committed 1 year ago

Verified ed0bf322

readme : update ui list (#5354)

biw committed 1 year ago

Verified 9a697d84

llama : add MiniCPM support (#5346)

runfuture committed 1 year ago

Verified 316c7faf

server : update `/props` with "total_slots" value (#5373)

jparkerweb committed 1 year ago

Verified f3e2b4fa

convert : fix TypeError on GPT-2 vocab.json (#5288)

Sang-Kil Park committed 1 year ago

Verified f68664ac

server : remove model.json endpoint (#5371)

z80maniac committed 1 year ago

Verified 213d1439

CUDA: mul_mat_vec_q max. batch size 8 -> 4 (#5370)

JohannesGaessler committed 1 year ago

Verified 17c97fb0

Update README.md (#5366)

ikawrakow committed 1 year ago

Verified b08f22c8

Slight quantization improvement for Q4_K and Q5_K (#5361)

ikawrakow committed 1 year ago

Verified f57fadc0

Older